confi new

config.json

@@ -1,14 +1,14 @@
 {
-  "_name_or_path": "yzsydlc/qwen-primeai-10",
+  "_name_or_path": "yzsydlc/qwen-primeai-10-v2",
   "architectures": [
     "QWenLMHeadModel"
   ],
   "attn_dropout_prob": 0.0,
   "auto_map": {
-    "AutoConfig": "yzsydlc/qwen-primeai-10--configuration_qwen.QWenConfig",
-    "AutoModelForCausalLM": "yzsydlc/qwen-primeai-10--modeling_qwen.QWenLMHeadModel"
+    "AutoConfig": "yzsydlc/qwen-primeai-10-v2--configuration_qwen.QWenConfig",
+    "AutoModelForCausalLM": "yzsydlc/qwen-primeai-10-v2--modeling_qwen.QWenLMHeadModel"
   },
-  "bf16": true,
+  "bf16": false,
   "emb_dropout_prob": 0.0,
   "fp16": false,
   "fp32": false,
@@ -27,16 +27,12 @@
   "rotary_pct": 1.0,
   "scale_attn_weights": true,
   "seq_length": 8192,
-  "softmax_in_fp32": false,
-  "tie_word_embeddings": false,
+    "tie_word_embeddings": false,
   "tokenizer_class": "QWenTokenizer",
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.38.1",
+    "transformers_version": "4.38.1",
   "use_cache": true,
-  "use_cache_kernel": false,
-  "use_cache_quantization": false,
-  "use_dynamic_ntk": true,
-  "use_flash_attn": true,
+    "use_dynamic_ntk": true,
+  "use_flash_attn": "auto",
   "use_logn_attn": true,
   "vocab_size": 151936
 }